The Pursuit of Diversity

Multi-objective Testing of Deep Reinforcement Learning Agents

Conference Paper (2026)
Author(s)

Antony Bartlett (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Cynthia Liem (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Annibale Panichella (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Research Group
Multimedia Computing
DOI related publication
https://doi.org/10.1007/978-3-032-24839-8_7 Final published version
More Info
expand_more
Publication Year
2026
Language
English
Research Group
Multimedia Computing
Pages (from-to)
97-112
Publisher
Springer Science and Business Media Deutschland GmbH
ISBN (print)
9783032248381
ISBN (electronic)
97830322483987
Event
17th International Symposium on Search-Based Software Engineering, SSBSE 2025 (2025-11-16 - 2025-11-16), Seoul, Korea, Republic of
Downloads counter
8
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Testing deep reinforcement learning (DRL) agents in safety-critical domains requires discovering diverse failure scenarios. Existing tools such as INDAGO rely on single-objective optimization focused solely on maximizing failure counts, but this does not ensure discovered scenarios are diverse or reveal distinct error types. We introduce INDAGO-Nexus, a multi-objective search approach that jointly optimizes for failure likelihood and test scenario diversity using multi-objective evolutionary algorithms with multiple diversity metrics and Pareto front selection strategies. We evaluated INDAGO-Nexus on three DRL agents: humanoid walker, self-driving car, and parking agent. On average, INDAGO-Nexus discovers up to 83% and 40% more unique failures (test effectiveness) than INDAGO in the SDC and Parking scenarios, respectively, while reducing time-to-failure by up to 67% across all agents.

Files

978-3-032-24839-8_7.pdf
(pdf | 0.543 Mb)
Taverne
warning

File under embargo until 30-10-2026